[CELL] oprofile: add support to OProfile for profiling CELL BE SPUs

From: Maynard Johnson <mpjohn@us.ibm.com>

This patch updates the existing arch/powerpc/oprofile/op_model_cell.c
to add in the SPU profiling capabilities.  In addition, a 'cell' subdirectory
was added to arch/powerpc/oprofile to hold Cell-specific SPU profiling code.
Exports spu_set_profile_private_kref and spu_get_profile_private_kref which
are used by OProfile to store private profile information in spufs data
structures.

Also incorporated several fixes from other patches (rrn).  Check pointer
returned from kzalloc.  Eliminated unnecessary cast.  Better error
handling and cleanup in the related area.  64-bit unsigned long parameter
was being demoted to 32-bit unsigned int and eventually promoted back to
unsigned long.

Signed-off-by: Carl Love <carll@us.ibm.com>
Signed-off-by: Maynard Johnson <mpjohn@us.ibm.com>
Signed-off-by: Bob Nelson <rrnelson@us.ibm.com>
Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com>
Acked-by: Paul Mackerras <paulus@samba.org>

5 files changed, 59 insertions, 5 deletions

diff --git a/include/asm-powerpc/oprofile_impl.h b/include/asm-powerpc/oprofile_impl.h
index 8d6b47f7b300..938fefb4c4bc 100644
--- a/include/asm-powerpc/oprofile_impl.h
+++ b/include/asm-powerpc/oprofile_impl.h
@@ -39,14 +39,16 @@ struct op_system_config {
 
 /* Per-arch configuration */
 struct op_powerpc_model {
-        void (*reg_setup) (struct op_counter_config *,
+        int (*reg_setup) (struct op_counter_config *,
                            struct op_system_config *,
                            int num_counters);
-        void (*cpu_setup) (struct op_counter_config *);
-        void (*start) (struct op_counter_config *);
-        void (*global_start) (struct op_counter_config *);
+        int  (*cpu_setup) (struct op_counter_config *);
+        int  (*start) (struct op_counter_config *);
+        int  (*global_start) (struct op_counter_config *);
         void (*stop) (void);
         void (*global_stop) (void);
+        int (*sync_start)(void);
+        int (*sync_stop)(void);
         void (*handle_interrupt) (struct pt_regs *,
                                   struct op_counter_config *);
         int num_counters;
diff --git a/include/asm-powerpc/spu.h b/include/asm-powerpc/spu.h
index 24f352da2869..a0f7fc8e23bb 100644
--- a/include/asm-powerpc/spu.h
+++ b/include/asm-powerpc/spu.h
@@ -138,6 +138,7 @@ struct spu {
         struct spu_runqueue *rq;
         unsigned long long timestamp;
         pid_t pid;
+        pid_t tgid;
         int class_0_pending;
         spinlock_t register_lock;
 
@@ -217,6 +218,20 @@ extern void spu_associate_mm(struct spu *spu, struct mm_struct *mm);
 struct mm_struct;
 extern void spu_flush_all_slbs(struct mm_struct *mm);
 
+/* This interface allows a profiler (e.g., OProfile) to store a ref
+ * to spu context information that it creates.  This caching technique
+ * avoids the need to recreate this information after a save/restore operation.
+ *
+ * Assumes the caller has already incremented the ref count to
+ * profile_info; then spu_context_destroy must call kref_put
+ * on prof_info_kref.
+ */
+void spu_set_profile_private_kref(struct spu_context *ctx,
+                                  struct kref *prof_info_kref,
+                                  void ( * prof_info_release) (struct kref *kref));
+
+void *spu_get_profile_private_kref(struct spu_context *ctx);
+
 /* system callbacks from the SPU */
 struct spu_syscall_block {
         u64 nr_ret;
diff --git a/include/linux/dcookies.h b/include/linux/dcookies.h
index 0fe7cdf326f7..98c69ab80c84 100644
--- a/include/linux/dcookies.h
+++ b/include/linux/dcookies.h
@@ -12,6 +12,7 @@
 
 #ifdef CONFIG_PROFILING
  
+#include <linux/dcache.h>
 #include <linux/types.h>
  
 struct dcookie_user;
diff --git a/include/linux/elf-em.h b/include/linux/elf-em.h
index 0311bad838b1..5834e843a946 100644
--- a/include/linux/elf-em.h
+++ b/include/linux/elf-em.h
@@ -20,7 +20,8 @@
 #define EM_PARISC       15      /* HPPA */
 #define EM_SPARC32PLUS  18      /* Sun's "v8plus" */
 #define EM_PPC          20      /* PowerPC */
-#define EM_PPC64        21       /* PowerPC64 */
+#define EM_PPC64        21       /* PowerPC64 */
+#define EM_SPU          23      /* Cell BE SPU */
 #define EM_SH           42      /* SuperH */
 #define EM_SPARCV9      43      /* SPARC v9 64-bit */
 #define EM_IA_64        50      /* HP/Intel IA-64 */
diff --git a/include/linux/oprofile.h b/include/linux/oprofile.h
index 0d514b252454..041bb31100f4 100644
--- a/include/linux/oprofile.h
+++ b/include/linux/oprofile.h
@@ -17,6 +17,26 @@
 #include <linux/spinlock.h>
 #include <asm/atomic.h>
  
+/* Each escaped entry is prefixed by ESCAPE_CODE
+ * then one of the following codes, then the
+ * relevant data.
+ * These #defines live in this file so that arch-specific
+ * buffer sync'ing code can access them.
+ */
+#define ESCAPE_CODE                     ~0UL
+#define CTX_SWITCH_CODE                 1
+#define CPU_SWITCH_CODE                 2
+#define COOKIE_SWITCH_CODE              3
+#define KERNEL_ENTER_SWITCH_CODE        4
+#define KERNEL_EXIT_SWITCH_CODE         5
+#define MODULE_LOADED_CODE              6
+#define CTX_TGID_CODE                   7
+#define TRACE_BEGIN_CODE                8
+#define TRACE_END_CODE                  9
+#define XEN_ENTER_SWITCH_CODE           10
+#define SPU_PROFILING_CODE              11
+#define SPU_CTX_SWITCH_CODE             12
+
 struct super_block;
 struct dentry;
 struct file_operations;
@@ -35,6 +55,14 @@ struct oprofile_operations {
         int (*start)(void);
         /* Stop delivering interrupts. */
         void (*stop)(void);
+        /* Arch-specific buffer sync functions.
+         * Return value = 0:  Success
+         * Return value = -1: Failure
+         * Return value = 1:  Run generic sync function
+         */
+        int (*sync_start)(void);
+        int (*sync_stop)(void);
+
         /* Initiate a stack backtrace. Optional. */
         void (*backtrace)(struct pt_regs * const regs, unsigned int depth);
         /* CPU identification string. */
@@ -56,6 +84,13 @@ int oprofile_arch_init(struct oprofile_operations * ops);
 void oprofile_arch_exit(void);
 
 /**
+ * Add data to the event buffer.
+ * The data passed is free-form, but typically consists of
+ * file offsets, dcookies, context information, and ESCAPE codes.
+ */
+void add_event_entry(unsigned long data);
+
+/**
  * Add a sample. This may be called from any context. Pass
  * smp_processor_id() as cpu.
  */